https://github.com/nvlabs/bongard-hoi
공식 코드Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent
Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking
Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative Models
NeedleBench: Can LLMs Do Retrieval and Reasoning in Information-Dense Context?
Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
GUI Odyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics
Fact-driven Logical Reasoning for Machine Reading Comprehension
Fact-driven Logical Reasoning for Machine Reading Comprehension
Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models
Medical Profile Model: Scientific and Practical Applications in Healthcare
Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment
Attacking Adversarial Defences by Smoothing the Loss Landscape
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation
Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
Improving Automatic Parallel Training via Balanced Memory Workload Optimization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.